drm/i915: Force GPU idle on suspend

To facilitate the next patch to allow preemptible kernels not to incur
the wrath of hangcheck, we need to ensure that we can still suspend and
shutdown. That is we will not be able to rely on hangcheck to terminate
a blocking kernel and instead must manually do so ourselves. The
advantage is that we can apply more pressure!

As we now perform a GPU reset to clean up any residual kernels, we leave
the GPU in an unknown state and in particular can not talk to the GuC
before we reinitialise it following resume. For example, we no longer
need to tell the GuC to suspend itself, as it is already reset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190307104530.21745-2-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eb90f73de06a8098118962d3eb1882c508e6cd83..df2f4f65c2a4ed8f08b78a9c1816316c2e8e2dc5 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3123,13 +3123,6 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915,
 
                lockdep_assert_held(&i915->drm.struct_mutex);
 
-               if (GEM_SHOW_DEBUG() && !timeout) {
-                       /* Presume that timeout was non-zero to begin with! */
-                       dev_warn(&i915->drm.pdev->dev,
-                                "Missed idle-completion interrupt!\n");
-                       GEM_TRACE_DUMP();
-               }
-
                err = wait_for_engines(i915);
                if (err)
                        return err;
@@ -4379,11 +4372,12 @@ int i915_gem_suspend(struct drm_i915_private *i915)
                                             I915_WAIT_INTERRUPTIBLE |
                                             I915_WAIT_LOCKED |
                                             I915_WAIT_FOR_IDLE_BOOST,
-                                            MAX_SCHEDULE_TIMEOUT);
-               if (ret && ret != -EIO)
+                                            I915_GEM_IDLE_TIMEOUT);
+               if (ret == -EINTR)
                        goto err_unlock;
 
-               assert_kernel_context_is_current(i915);
+               /* Forcibly cancel outstanding work and leave the gpu quiet. */
+               i915_gem_set_wedged(i915);
        }
        i915_retire_requests(i915); /* ensure we flush after wedging */
 
@@ -4398,15 +4392,11 @@ int i915_gem_suspend(struct drm_i915_private *i915)
         */
        drain_delayed_work(&i915->gt.idle_work);
 
-       intel_uc_suspend(i915);
-
        /*
         * Assert that we successfully flushed all the work and
         * reset the GPU back to its idle, low power state.
         */
-       WARN_ON(i915->gt.awake);
-       if (WARN_ON(!intel_engines_are_idle(i915)))
-               i915_gem_set_wedged(i915); /* no hope, discard everything */
+       GEM_BUG_ON(i915->gt.awake);
 
        intel_runtime_pm_put(i915, wakeref);
        return 0;